Update app.py

app.py

@@ -1,7 +1,6 @@
 import os
 import time
 import json
-import math
 import random
 from dataclasses import dataclass
 from typing import Any, Dict, List, Optional, Tuple
@@ -10,7 +9,6 @@ import numpy as np
 import pandas as pd
 import streamlit as st
 import plotly.express as px
-import plotly.graph_objects as go
 from streamlit_option_menu import option_menu
 from faker import Faker
 from datetime import datetime, timedelta
@@ -81,12 +79,23 @@ st.markdown(
 )
 
 # =============================
-# Config & LLM Client (robust, version-agnostic)
+# Currency Helper (₹)
+# =============================
+CURRENCY = "₹"
+
+def fmt_currency(x: float) -> str:
+    try:
+        return f"{CURRENCY}{x:,.0f}"
+    except Exception:
+        return f"{CURRENCY}{x}"
+
+# =============================
+# Config & LLM Client (resilient)
 # =============================
 @dataclass
 class LLMConfig:
-    provider: str = os.getenv("LLM_PROVIDER", "openai").lower()  # openai | azure | compatible
-    base_url: Optional[str] = os.getenv("OPENAI_BASE_URL")  # for compatible endpoints
+    provider: str = os.getenv("LLM_PROVIDER", "openai").lower()
+    base_url: Optional[str] = os.getenv("OPENAI_BASE_URL")
     api_key: Optional[str] = (
         os.getenv("OPENAI_API_KEY")
         or os.getenv("OPENAI_API_TOKEN")
@@ -95,7 +104,7 @@ class LLMConfig:
     model: str = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
     timeout: int = int(os.getenv("OPENAI_TIMEOUT", "45"))
     max_retries: int = int(os.getenv("OPENAI_MAX_RETRIES", "5"))
-    temperature: float = float(os.getenv("OPENAI_TEMPERATURE", "0.6"))
+    temperature: float = float(os.getenv("OPENAI_TEMPERATURE", "0.5"))
 
 
 def _post_json(url: str, headers: Dict[str, str], payload: Dict[str, Any], timeout: int):
@@ -104,12 +113,6 @@ def _post_json(url: str, headers: Dict[str, str], payload: Dict[str, Any], timeo
 
 
 class UniversalLLMClient:
-    """A resilient client that works with OpenAI, Azure OpenAI, and compatible APIs.
-    - Prefers /chat/completions
-    - Falls back to /responses if available
-    - Retries with exponential backoff and respects Retry-After
-    """
-
     def __init__(self, cfg: LLMConfig):
         self.cfg = cfg
         self.available = bool(cfg.api_key)
@@ -121,20 +124,11 @@ class UniversalLLMClient:
         return {"Authorization": f"Bearer {self.cfg.api_key}", "Content-Type": "application/json"}
 
     def _base_url(self) -> str:
-        if self.cfg.provider == "azure":
-            # Use Azure env format if provided
-            endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
-            api_version = os.getenv("AZURE_OPENAI_API_VERSION", "2024-02-15-preview")
-            deployment = os.getenv("AZURE_OPENAI_DEPLOYMENT", self.cfg.model)
-            # Azure uses deployment name in path
-            return f"{endpoint}/openai/deployments/{deployment}?api-version={api_version}"
         return (self.cfg.base_url or "https://api.openai.com/v1").rstrip("/")
 
     def _smoke_test(self):
         try:
-            _ = self.chat([
-                {"role": "user", "content": "ping"}
-            ], max_tokens=4)
+            _ = self.chat([{"role": "user", "content": "ping"}], max_tokens=4)
         except Exception as e:
             self.available = False
             self.last_error = str(e)
@@ -142,22 +136,15 @@ class UniversalLLMClient:
     def chat(self, messages: List[Dict[str, str]], max_tokens: int = 400) -> str:
         if not self.available:
             raise RuntimeError("No API key configured")
-
         headers = self._headers()
         base = self._base_url()
-
-        # Endpoint selection
-        chat_url = f"{base}/chat/completions" if self.cfg.provider != "azure" else f"{base}&api-version-override=false"  # azure path already includes params
-        responses_url = f"{base}/responses"
-
+        chat_url = f"{base}/chat/completions"
         payload = {
             "model": self.cfg.model,
             "messages": messages,
             "max_tokens": max_tokens,
             "temperature": self.cfg.temperature,
         }
-
-        # Retry with backoff
         delay = 1.0
         for attempt in range(self.cfg.max_retries):
             try:
@@ -165,23 +152,10 @@ class UniversalLLMClient:
                 if resp.status_code == 200:
                     data = resp.json()
                     return data["choices"][0]["message"]["content"].strip()
-                # Try /responses fallback for some providers
-                if resp.status_code in (404, 400):
-                    alt = _post_json(
-                        responses_url,
-                        headers,
-                        {"model": self.cfg.model, "input": messages, "max_output_tokens": max_tokens, "temperature": self.cfg.temperature},
-                        self.cfg.timeout,
-                    )
-                    if alt.status_code == 200:
-                        return alt.json()["output"][0]["content"][0]["text"].strip()
-
                 if resp.status_code in (429, 500, 502, 503, 504):
-                    retry_after = float(resp.headers.get("Retry-After", delay))
-                    time.sleep(retry_after)
+                    time.sleep(delay)
                     delay = min(delay * 2, 8.0)
                     continue
-                # Other errors → raise
                 try:
                     j = resp.json()
                     msg = j.get("error", {}).get("message", str(j))
@@ -196,13 +170,11 @@ class UniversalLLMClient:
                 delay = min(delay * 2, 8.0)
         raise RuntimeError("Exhausted retries")
 
-
 # =============================
-# Data Generation & Utils
+# Data Generation
 # =============================
 @st.cache_data(show_spinner=False)
 def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, pd.DataFrame]:
-    """Generate richer synthetic SAP S/4HANA procurement data, including lead times and late flags."""
     fake = Faker()
     np.random.seed(seed)
     random.seed(seed)
@@ -218,7 +190,6 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
     ]
 
     purchase_orders: List[Dict[str, Any]] = []
-    today = datetime.utcnow().date()
 
     for i in range(900):
         order_date = fake.date_between(start_date='-24m', end_date='today')
@@ -239,8 +210,6 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
             'order_date': order_date,
             'promised_date': promised_date,
             'delivery_date': delivery_date,
-            'lead_time_days': (delivery_date - order_date).days,
-            'promised_days': promised_days,
             'late_delivery': late,
             'order_value': order_value,
             'quantity': qty,
@@ -248,7 +217,7 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
             'status': random.choice(['Open', 'Delivered', 'Invoiced', 'Paid']),
             'plant': random.choice(['Plant_001', 'Plant_002', 'Plant_003']),
             'buyer': fake.name(),
-            'currency': 'EUR',
+            'currency': 'INR',
             'payment_terms': random.choice(['30 Days', '45 Days', '60 Days', '90 Days']),
             'quality_score': round(np.clip(np.random.normal(8.5, 0.8), 5.0, 10.0), 1),
         }
@@ -270,11 +239,6 @@ def generate_synthetic_procurement_data(seed: int = 42) -> Tuple[pd.DataFrame, p
     spend_df = pd.DataFrame(spend_rows)
     return po_df, spend_df
 
-
-def eur(x: float) -> str:
-    return f"€{x:,.0f}"
-
-
 # =============================
 # Analytics Engine
 # =============================
@@ -284,9 +248,8 @@ class ProcurementAnalytics:
         self.df['order_date'] = pd.to_datetime(self.df['order_date'])
         self.df['month'] = self.df['order_date'].dt.to_period('M').dt.to_timestamp()
 
-    @st.cache_data(show_spinner=False)
-    def kpis(_self, df_hash: int) -> Dict[str, Any]:
-        df = _self.df
+    def kpis(self) -> Dict[str, Any]:
+        df = self.df
         return {
             'total_spend': float(df['order_value'].sum()),
             'avg_order_value': float(df['order_value'].mean()),
@@ -296,14 +259,10 @@ class ProcurementAnalytics:
         }
 
     def category_spend(self) -> pd.DataFrame:
-        return (
-            self.df.groupby('material_category', as_index=False)['order_value'].sum()
-            .sort_values('order_value', ascending=False)
-        )
+        return self.df.groupby('material_category', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False)
 
     def vendor_spend(self, top_n: int = 8) -> pd.DataFrame:
-        g = self.df.groupby('vendor', as_index=False)['order_value'].sum()
-        return g.sort_values('order_value', ascending=False).head(top_n)
+        return self.df.groupby('vendor', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False).head(top_n)
 
     def monthly_spend(self) -> pd.DataFrame:
         return self.df.groupby('month', as_index=False)['order_value'].sum().sort_values('month')
@@ -314,154 +273,179 @@ class ProcurementAnalytics:
             on_time=('late_delivery', lambda s: 1 - s.mean()),
             quality=('quality_score', 'mean'),
             orders=('po_number', 'count'),
-            lead_time=('lead_time_days', 'mean'),
         )
         g['on_time'] = (g['on_time'] * 100).round(1)
         g['quality'] = g['quality'].round(2)
-        g['lead_time'] = g['lead_time'].round(1)
         g['total_spend'] = g['total_spend'].round(2)
         return g.sort_values('total_spend', ascending=False)
 
-    def anomalies(self) -> pd.DataFrame:
-        # Simple IQR for order_value anomalies
-        q1, q3 = self.df['order_value'].quantile([0.25, 0.75])
-        iqr = q3 - q1
-        hi = q3 + 1.5 * iqr
-        lo = max(0, q1 - 1.5 * iqr)
-        a = self.df[(self.df['order_value'] > hi) | (self.df['order_value'] < lo)].copy()
-        a['anomaly_reason'] = np.where(a['order_value'] > hi, 'High value', 'Low value')
-        return a.sort_values('order_value', ascending=False).head(50)
-
-    def simulate_vendor_consolidation(self, keep_top: int) -> Dict[str, Any]:
-        g = self.df.groupby('vendor')['order_value'].sum().sort_values(ascending=False)
-        kept_vendors = list(g.head(keep_top).index)
-        kept_spend = self.df[self.df['vendor'].isin(kept_vendors)]['order_value'].sum()
-        total_spend = self.df['order_value'].sum()
-        share = kept_spend / total_spend if total_spend else 0
-        est_savings = 0.05 + (0.12 * (1 - share))  # heuristic: better leverage when consolidating
-        return {
-            'kept_vendors': kept_vendors,
-            'kept_share': share,
-            'estimated_savings_pct': max(0.03, min(0.18, est_savings)),
-        }
+    # helper: top N with shares
+    def top_n_categories(self, n: int = 3) -> List[Tuple[str, float]]:
+        cat = self.category_spend()
+        total = float(cat['order_value'].sum()) or 1.0
+        return [(r['material_category'], (r['order_value']/total)*100) for _, r in cat.head(n).iterrows()]
 
+    def top_n_vendors(self, n: int = 3) -> List[Tuple[str, float]]:
+        ven = self.df.groupby('vendor', as_index=False)['order_value'].sum().sort_values('order_value', ascending=False)
+        total = float(ven['order_value'].sum()) or 1.0
+        return [(r['vendor'], (r['order_value']/total)*100) for _, r in ven.head(n).iterrows()]
 
 # =============================
-# Agent (uses UniversalLLMClient with safe fallback)
+# Agent with tighter prompts & INR formatting
 # =============================
 class UniversalProcurementAgent:
     def __init__(self, po_df: pd.DataFrame, spend_df: pd.DataFrame, client: UniversalLLMClient):
         self.po_data = po_df
         self.spend_data = spend_df
         self.llm = client
-
-    def llm_status(self) -> Dict[str, Any]:
-        return {
-            "api_key_available": bool(self.llm.cfg.api_key),
-            "llm_available": self.llm.available,
-            "last_error": self.llm.last_error or "Connected successfully" if self.llm.available else "Unavailable",
-            "provider": self.llm.cfg.provider,
-            "model": self.llm.cfg.model,
-            "base_url": self.llm.cfg.base_url or "https://api.openai.com/v1",
-        }
-
-    def _rule_summary(self) -> str:
-        total_spend = float(self.po_data['order_value'].sum())
-        on_time = float((~self.po_data['late_delivery']).mean()) * 100
-        quality = float(self.po_data['quality_score'].mean())
-        top_cat = self.po_data.groupby('material_category')['order_value'].sum().idxmax()
-        top_vendor = self.po_data.groupby('vendor')['order_value'].sum().idxmax()
-        return (
-            "🤖 **[Smart Analysis - Rule-Based Engine]**\n"
-            "**Executive Snapshot**\n"
-            f"• Total spend: {eur(total_spend)} across {len(self.po_data):,} POs\n"
-            f"• On-time delivery: {on_time:.1f}%  • Avg quality: {quality:.1f}/10\n"
-            f"• Top category: {top_cat}  • Lead vendor: {top_vendor}\n\n"
-            "**Opportunities**\n"
-            "• Consolidate long tail vendors to improve pricing power (5–12% potential).\n"
-            "• Tighten SLAs for late deliveries and extend performance-based contracts.\n"
-            "• Automate low-value buys to reduce cycle time."
-        )
+        self.analytics = ProcurementAnalytics(po_df)
 
     def executive_summary(self) -> str:
         if not self.llm.available:
             return self._rule_summary()
+        k = self.analytics.kpis()
+        top_cats = self.analytics.top_n_categories(3)
+        top_vens = self.analytics.top_n_vendors(3)
         data_summary = {
-            "total_spend": float(self.po_data['order_value'].sum()),
+            "total_spend": k['total_spend'],
             "total_orders": int(len(self.po_data)),
             "vendor_count": int(self.po_data['vendor'].nunique()),
-            "avg_order_value": float(self.po_data['order_value'].mean()),
-            "on_time_delivery": float((~self.po_data['late_delivery']).mean()),
-            "avg_quality": float(self.po_data['quality_score'].mean()),
+            "avg_order_value": k['avg_order_value'],
+            "on_time_delivery": k['on_time_rate'],
+            "avg_quality": k['quality_avg'],
+            "top_categories": top_cats,
+            "top_vendors": top_vens,
         }
         messages = [
-            {"role": "system", "content": "You are a senior procurement analyst with expertise in SAP S/4HANA. Be concise, metric-driven, and actionable."},
+            {"role": "system", "content": (
+                "You are a senior procurement analyst. Use bullet points, be concise, and always use the ₹ symbol. "
+                "When summarizing, include top categories and vendors with percentages, then 2-3 quantified actions."
+            )},
             {"role": "user", "content": (
-                "Create an executive summary covering: 1) overview (2-3 sentences), 2) KPI highlights, 3) risks/alerts, 4) 3-4 strategic recommendations with quantified impact.\n"
+                f"Executive summary. Format amounts with commas (e.g., ₹12,34,567).
+
+"
                 f"Data: {json.dumps(data_summary)}"
             )},
         ]
         try:
-            return "🧠 **[AI-Powered Analysis]**\n\n" + self.llm.chat(messages, max_tokens=650)
+            return "🧠 **[AI-Powered Analysis]**
+
+" + self.llm.chat(messages, max_tokens=550)
         except Exception as e:
-            return self._rule_summary() + f"\n\n*AI fallback due to: {e}*"
+            return self._rule_summary() + f"
+
+*AI fallback due to: {e}*"
+
+    def _rule_summary(self) -> str:
+        k = self.analytics.kpis()
+        top_c = self.analytics.top_n_categories(3)
+        top_v = self.analytics.top_n_vendors(3)
+        topc_str = ", ".join([f"{n} – {s:.0f}%" for n, s in top_c])
+        topv_str = ", ".join([f"{n} – {s:.0f}%" for n, s in top_v])
+        return (
+            "🤖 **[Rule-Based Summary]**
+"
+            f"• Total spend: {fmt_currency(k['total_spend'])} across {len(self.po_data):,} POs
+"
+            f"• On-time delivery: {k['on_time_rate']*100:.1f}% | Avg quality: {k['quality_avg']:.1f}/10
+"
+            f"• Top categories: {topc_str}
+"
+            f"• Top vendors: {topv_str}
+"
+            "Actions: Consolidate long tail; multi-year terms with top vendors; auto-approve low-value POs."
+        )
 
     def chat_with_data(self, question: str) -> str:
         if not self.llm.available:
             return self._rule_answer(question)
+        k = self.analytics.kpis()
+        top_c = self.analytics.top_n_categories(3)
+        top_v = self.analytics.top_n_vendors(3)
         context = {
-            "total_spend": float(self.po_data['order_value'].sum()),
+            "total_spend": k['total_spend'],
             "orders": int(len(self.po_data)),
             "vendors": int(self.po_data['vendor'].nunique()),
-            "on_time": float((~self.po_data['late_delivery']).mean()),
-            "quality": float(self.po_data['quality_score'].mean()),
+            "on_time": k['on_time_rate'],
+            "quality": k['quality_avg'],
+            "top_categories": top_c,
+            "top_vendors": top_v,
         }
+        style_rules = (
+            "Rules: Answer in ≤6 bullet points, use ₹, no generic how-to steps. "
+            "If question mentions spend, list top 3 categories and top 3 vendors with shares. "
+            "If vendors, show best & worst by on-time and spend. If risk, show late % and actions."
+        )
         messages = [
-            {"role": "system", "content": "You are an expert procurement co-pilot. Use the provided context and respond with precise metrics and concrete actions."},
-            {"role": "user", "content": f"Question: {question}\nContext: {json.dumps(context)}"},
+            {"role": "system", "content": "You are a precise procurement co-pilot. Be direct, metric-first, and action-oriented."},
+            {"role": "user", "content": f"Q: {question}
+
+Context: {json.dumps(context)}
+
+{style_rules}"},
         ]
         try:
-            return "🧠 **[AI Response]**\n\n" + self.llm.chat(messages, max_tokens=450)
+            return "🧠 **[AI Response]**
+
+" + self.llm.chat(messages, max_tokens=450)
         except Exception as e:
-            return self._rule_answer(question) + f"\n\n*AI fallback due to: {e}*"
+            return self._rule_answer(question) + f"
+
+*AI fallback due to: {e}*"
 
     def _rule_answer(self, question: str) -> str:
         q = question.lower()
-        if any(w in q for w in ["spend", "cost", "budget"]):
-            total = float(self.po_data['order_value'].sum())
-            monthly = total / max(1, self.po_data['order_date'].nunique()/30)
-            top_cat = self.po_data.groupby('material_category')['order_value'].sum().idxmax()
-            return (
-                "🤖 **[Smart Analysis] Spend**\n"
-                f"• Total spend: {eur(total)}\n"
-                f"• Monthly average (approx): {eur(monthly)}\n"
-                f"• Top category: {top_cat}\n"
-                "Tip: prioritize competitive events for the top 2 categories to unlock 4–8% savings."
-            )
-        if any(w in q for w in ["vendor", "supplier", "partner"]):
+        k = self.analytics.kpis()
+        top_c = self.analytics.top_n_categories(3)
+        top_v = self.analytics.top_n_vendors(3)
+        if "spend" in q or "spending" in q or "cost" in q:
+            lines = [
+                f"• Total spend: {fmt_currency(k['total_spend'])}",
+                "• Top categories: " + ", ".join([f"{n} – {s:.0f}%" for n, s in top_c]),
+                "• Top vendors: " + ", ".join([f"{n} – {s:.0f}%" for n, s in top_v]),
+                "• Action: Run sourcing events for top 2 categories; target 8–12% savings via volume tiers.",
+            ]
+            return "🤖 **[Rule-Based Spend]**
+" + "
+".join(lines)
+        if "vendor" in q or "supplier" in q or "partner" in q:
             vp = self.po_data.groupby('vendor').agg(
                 spend=('order_value','sum'),
-                on_time=('late_delivery', lambda s: 1 - s.mean()),
-            ).sort_values('spend', ascending=False).head(1)
-            top = vp.index[0]
-            on_time = float(vp.iloc[0]['on_time'])*100
-            return (
-                "🤖 **[Smart Analysis] Vendor**\n"
-                f"• Top vendor: {top} • On-time: {on_time:.1f}%\n"
-                "Action: lock in volume tiers and add delivery penalties to the contract."
-            )
-        if any(w in q for w in ["risk", "late", "delay"]):
-            late_rate = float(self.po_data['late_delivery'].mean())*100
-            return (
-                "🤖 **[Smart Analysis] Risk**\n"
-                f"• Late delivery rate: {late_rate:.1f}%\n"
-                "Action: add buffer to planning lead times and escalate chronic late suppliers."
-            )
+                late_rate=('late_delivery','mean'),
+                quality=('quality_score','mean'),
+            ).sort_values('spend', ascending=False)
+            best = vp.head(1)
+            worst = vp.sort_values('late_rate', ascending=False).head(1)
+            bname, wname = best.index[0], worst.index[0]
+            blate = float(best.iloc[0]['late_rate'])*100
+            wlate = float(worst.iloc[0]['late_rate'])*100
+            lines = [
+                f"• Best by spend: {bname} (late {blate:.1f}%)",
+                f"• Worst by late deliveries: {wname} (late {wlate:.1f}%)",
+                "• Action: Extend terms with best performer; corrective plan and SLA penalties for the worst.",
+            ]
+            return "🤖 **[Rule-Based Vendor]**
+" + "
+".join(lines)
+        if "risk" in q or "late" in q or "delay" in q:
+            late = float(self.po_data['late_delivery'].mean())*100
+            lines = [
+                f"• Late delivery rate: {late:.1f}%",
+                "• Action: Add 5–10 day buffers; fast-track chronic offenders; add service credits for misses.",
+            ]
+            return "🤖 **[Rule-Based Risk]**
+" + "
+".join(lines)
+        # default
         return (
-            "🤖 **[Smart Analysis]** I can help with spend, vendor performance, risk, savings, and trends. Try: \"Where can I save 10%?\""
+            "🤖 **[Rule-Based]**
+"
+            "• I can analyze spend (top categories/vendors), vendor performance (best/worst), risk (late %), and trends.
+"
+            f"• Snapshot: {fmt_currency(k['total_spend'])}, {len(self.po_data):,} POs, {self.po_data['vendor'].nunique()} vendors, on-time {k['on_time_rate']*100:.1f}%"
         )
 
-
 # =============================
 # App State & Initialization
 # =============================
@@ -478,8 +462,12 @@ client = get_llm_client()
 agent = UniversalProcurementAgent(st.session_state.po_df, st.session_state.spend_df, client)
 analytics = ProcurementAnalytics(st.session_state.po_df)
 
-status = agent.llm_status()
-api_status = "🟢 Connected" if status['llm_available'] else "🔴 Not Connected"
+status = {
+    "available": client.available,
+    "last_error": client.last_error or "OK",
+    "model": client.cfg.model,
+}
+api_status = "🟢 Connected" if status['available'] else "🔴 Not Connected"
 
 # =============================
 # Header
@@ -489,7 +477,7 @@ st.markdown(
 <div class="main-header">
   <h1>🤖 SAP S/4HANA Agentic AI Procurement Analytics</h1>
   <p>Autonomous Intelligence for Procurement Excellence</p>
-  <small>OpenAI: {api_status} · Data: {len(st.session_state.po_df):,} POs</small>
+  <small>LLM: {api_status} · Data: {len(st.session_state.po_df):,} POs</small>
 </div>
 """,
     unsafe_allow_html=True,
@@ -501,21 +489,10 @@ st.markdown(
 with st.sidebar:
     st.markdown("### 🤖 AI System Status")
     st.markdown(f"**Connection:** {api_status}")
-    st.markdown(f"**Provider:** {status['provider']}  ")
     st.markdown(f"**Model:** {status['model']}")
 
     with st.expander("🔍 System Information"):
-        safe = status.copy()
-        # Do not expose API key
-        st.json({k: v for k, v in safe.items() if k != 'api_key'})
-
-    if st.button("🔄 Test AI Connection"):
-        if status['llm_available']:
-            st.success("LLM is reachable and ready.")
-        else:
-            st.error(f"LLM unavailable: {status['last_error']}")
-
-    st.markdown("---")
+        st.json(status)
 
     selected = option_menu(
         "Navigation",
@@ -545,13 +522,13 @@ if selected == "🏠 Dashboard":
     </div>
     """, unsafe_allow_html=True)
 
-    k = analytics.kpis(hash(tuple(st.session_state.po_df['po_number'])))
+    k = analytics.kpis()
 
     c1, c2, c3, c4 = st.columns(4)
     with c1:
-        st.markdown(f"<div class='metric-card'><h3 style='color: var(--primary-color); margin:0;'>Total Spend</h3><h2 style='margin: .5rem 0;'>{eur(k['total_spend'])}</h2><p style='color:#28a745;margin:0;'>📈 Active Portfolio</p></div>", unsafe_allow_html=True)
+        st.markdown(f"<div class='metric-card'><h3 style='color: var(--primary-color); margin:0;'>Total Spend</h3><h2 style='margin: .5rem 0;'>{fmt_currency(k['total_spend'])}</h2><p style='color:#28a745;margin:0;'>📈 Active Portfolio</p></div>", unsafe_allow_html=True)
     with c2:
-        st.markdown(f"<div class='metric-card'><h3 style='color: var(--primary-color); margin:0;'>Avg Order Value</h3><h2 style='margin: .5rem 0;'>{eur(k['avg_order_value'])}</h2><p style='color:#17a2b8;margin:0;'>📊 Order Efficiency</p></div>", unsafe_allow_html=True)
+        st.markdown(f"<div class='metric-card'><h3 style='color: var(--primary-color); margin:0;'>Avg Order Value</h3><h2 style='margin: .5rem 0;'>{fmt_currency(k['avg_order_value'])}</h2><p style='color:#17a2b8;margin:0;'>📊 Order Efficiency</p></div>", unsafe_allow_html=True)
     with c3:
         st.markdown(f"<div class='metric-card'><h3 style='color: var(--primary-color); margin:0;'>Active Vendors</h3><h2 style='margin: .5rem 0;'>{k['active_vendors']}</h2><p style='color:#6f42c1;margin:0;'>🤝 Strategic Partners</p></div>", unsafe_allow_html=True)
     with c4:
@@ -580,23 +557,25 @@ if selected == "🏠 Dashboard":
         st.plotly_chart(fig3, use_container_width=True)
 
     with colD:
-        ano = analytics.anomalies()
-        st.markdown("#### 🔎 High/Low Value Anomalies (Top 50)")
-        st.dataframe(ano[['po_number','vendor','material_category','order_value','anomaly_reason']].reset_index(drop=True), use_container_width=True, height=380)
+        st.markdown("#### 🔎 Quick Top Areas")
+        tcat = ", ".join([f"{n} – {s:.0f}%" for n, s in analytics.top_n_categories(3)])
+        tven = ", ".join([f"{n} – {s:.0f}%" for n, s in analytics.top_n_vendors(3)])
+        st.markdown(f"**Top Categories:** {tcat}")
+        st.markdown(f"**Top Vendors:** {tven}")
 
 elif selected == "💬 AI Chat":
     st.markdown("### 💬 Chat with Your Procurement Data")
     st.markdown(f"""
-    <div class="ai-insight">
+    <div class=\"ai-insight\">
         <h4>🤖 Universal AI Assistant</h4>
-        <p>Ask me anything about your procurement data! I'm provider-agnostic and resilient to API versions.</p>
-        <p><small>Status: {api_status} | Provider: {status['provider']} | Model: {status['model']}</small></p>
+        <p>Ask me anything about your procurement data. I will answer with crisp bullets and actual metrics.</p>
+        <p><small>Status: {api_status} | Model: {status['model']}</small></p>
     </div>
     """, unsafe_allow_html=True)
 
     if "messages" not in st.session_state:
         st.session_state.messages = [
-            {"role": "assistant", "content": "Hello! I loaded your data and I'm ready to help—try asking about spend, vendors, or risk."}
+            {"role": "assistant", "content": "Hello! Try: 'What are my biggest spending areas?' or 'Which vendor is the weakest on delivery?'"}
         ]
 
     for m in st.session_state.messages:
@@ -613,9 +592,13 @@ elif selected == "💬 AI Chat":
             st.markdown(reply)
         st.session_state.messages.append({"role": "assistant", "content": reply})
 
-    st.markdown("#### 💡 Try quick questions:")
+    st.markdown("#### 💡 Quick asks:")
     c1, c2, c3 = st.columns(3)
-    qs = ["What are my biggest spending areas?", "How are my vendors performing?", "Where can I save 10%?"]
+    qs = [
+        "What are my biggest spending areas?",
+        "Which vendors perform the best and worst?",
+        "What risks should I monitor right now?",
+    ]
     for i, (c, q) in enumerate(zip([c1, c2, c3], qs)):
         with c:
             if st.button(f"💭 {q}", key=f"q_{i}"):
@@ -627,11 +610,10 @@ elif selected == "📊 Analytics":
     st.markdown("### 📈 Advanced Analytics Dashboard")
     vp = analytics.vendor_performance()
     st.dataframe(vp.rename(columns={
-        'total_spend': 'Total Spend (€)',
+        'total_spend': 'Total Spend (₹)',
         'on_time': 'On-Time Delivery %',
         'quality': 'Quality Score',
         'orders': 'Order Count',
-        'lead_time': 'Avg Lead Time (days)'
     }), use_container_width=True)
 
     st.download_button(
@@ -644,14 +626,20 @@ elif selected == "📊 Analytics":
 elif selected == "🧪 What‑If":
     st.markdown("### 🧪 What‑If: Vendor Consolidation Simulator")
     top_n = st.slider("Keep top N vendors by spend", min_value=2, max_value=10, value=6, step=1)
-    sim = analytics.simulate_vendor_consolidation(keep_top=top_n)
 
-    kept_names = ", ".join(sim['kept_vendors'])
+    g = st.session_state.po_df.groupby('vendor')['order_value'].sum().sort_values(ascending=False)
+    kept_vendors = list(g.head(top_n).index)
+    kept_spend = st.session_state.po_df[st.session_state.po_df['vendor'].isin(kept_vendors)]['order_value'].sum()
+    total_spend = st.session_state.po_df['order_value'].sum()
+    share = (kept_spend/total_spend) if total_spend else 0
+    est_savings = max(0.03, min(0.18, 0.05 + (0.12 * (1 - share))))
+
+    kept_names = ", ".join(kept_vendors)
     st.markdown(
         f"""
         <div class='alert alert-info'>
-            <strong>Scenario:</strong> Keep top <b>{top_n}</b> vendors. Estimated addressable spend share: <b>{sim['kept_share']*100:.1f}%</b>.<br/>
-            <strong>Potential savings:</strong> <b>{sim['estimated_savings_pct']*100:.1f}%</b> (heuristic).<br/>
+            <strong>Scenario:</strong> Keep top <b>{top_n}</b> vendors. Addressable share: <b>{share*100:.1f}%</b>.<br/>
+            <strong>Potential savings:</strong> <b>{est_savings*100:.1f}%</b> (heuristic).<br/>
             <small>Kept Vendors:</small> {kept_names}
         </div>
         """,
@@ -659,7 +647,7 @@ elif selected == "🧪 What‑If":
     )
 
     if st.checkbox("Show detailed vendor spend"):
-        st.dataframe(analytics.vendor_spend(top_n=999), use_container_width=True)
+        st.dataframe(g.reset_index().rename(columns={'index':'vendor','order_value':'spend (₹)'}), use_container_width=True)
 
 elif selected == "🎯 Recommendations":
     st.markdown("### 🚀 Strategic Recommendations")
@@ -688,8 +676,8 @@ st.markdown("---")
 st.markdown(
     f"""
 <div style="text-align:center; padding: 1rem; color:#666;">
-  <p>🤖 <strong>Universal AI Procurement Analytics</strong> | Provider‑agnostic LLM integration with resilient fallbacks</p>
-  <p><em>Demo with synthetic data • {len(st.session_state.po_df):,} orders • OpenAI {api_status}</em></p>
+  <p>🤖 <strong>Universal AI Procurement Analytics</strong> | Crisp, metric-first answers in ₹</p>
+  <p><em>Demo with synthetic data • {len(st.session_state.po_df):,} orders • LLM {api_status}</em></p>
 </div>
 """,
     unsafe_allow_html=True,